INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ible

-0.75

 promise

-0.70

 benef

-0.67

 benefits

-0.66

 liabilities

-0.66

 antidote

-0.64

 survivor

-0.64

 inher

-0.63

 overlook

-0.62

 outper

-0.61

POSITIVE LOGITS

eah

0.76

 Metatron

0.76

 Allaah

0.73

Sense

0.72

istration

0.72

tm

0.71

esan

0.71

Tai

0.70

manship

0.70

Ear

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.